I am trying to write a vanilla autoencoder for compressing 13 images. However I am getting the following error:
ValueError: train argument is not supported anymore. Use chainer.using_config
The shape of images is (21,28,3).
filelist = 'ex1.png', 'ex2.png',...11 other images
x = np.array([np.array(Image.open(fname)) for fname in filelist])
xs = x.astype('float32')/255.
class Autoencoder(Chain):
def __init__(self, activation=F.relu):
super().__init__()
with self.init_scope():
# encoder part
self.l1 = L.Linear(1764,800)
self.l2 = L.Linear(800,300)
# decoder part
self.l3 = L.Linear(300,800)
self.l4 = L.Linear(800,1764)
self.activation = activation
def forward(self,x):
h = self.encode(x)
x_recon = self.decode(h)
return x_recon
def __call__(self,x):
x_recon = self.forward(x)
loss = F.mean_squared_error(h, x)
return loss
def encode(self, x, train=True):
h = F.dropout(self.activation(self.l1(x)), train=train)
return self.activation(self.l2(x))
def decode(self, h, train=True):
h = self.activation(self.l3(h))
return self.l4(x)
n_epoch = 5
batch_size = 2
model = Autoencoder()
optimizer = optimizers.SGD(lr=0.05).setup(model)
train_iter = iterators.SerialIterator(xs,batch_size)
valid_iter = iterators.SerialIterator(xs,batch_size)
updater = training.StandardUpdater(train_iter,optimizer)
trainer = training.Trainer(updater,(n_epoch,"epoch"),out="result")
from chainer.training import extensions
trainer.extend(extensions.Evaluator(valid_iter, model, device=gpu_id))
trainer.run()
Is the issue because of the number of nodes in the model or otherwise?
You need to wirte "decoder" part.
When you take mean_squared_error loss, the shape of h and x must be same.
AutoEncoder will encode original x to small space (100-dim) h, but after that we need to reconstruct x' from this h by adding decoder part.
Then loss can be calculated on this reconstructed x'.
For example, as follows (sorry i have not test it to run)
train argument is handled by global configs, so you do not need train argument in dropout function.
class Autoencoder(Chain):
def __init__(self, activation=F.relu):
super().__init__()
with self.init_scope():
# encoder part
self.l1 = L.Linear(1308608,500)
self.l2 = L.Linear(500,100)
# decoder part
self.l3 = L.Linear(100,500)
self.l4 = L.Linear(500,1308608)
self.activation = activation
def forward(self,x):
h = self.encode(x)
x_recon = self.decode(h)
return x_recon
def __call__(self,x):
x_recon = self.forward(x)
loss = F.mean_squared_error(h, x)
return loss
def encode(self, x):
h = F.dropout(self.activation(self.l1(x)))
return self.activation(self.l2(x))
def decode(self, h, train=True):
h = self.activation(self.l3(h))
return self.l4(x)
class Autoencoder(Chain):
def __init__(self, activation=F.relu):
super().__init__()
with self.init_scope():
# encoder part
self.l1 = L.Linear(1308608,500)
self.l2 = L.Linear(500,100)
# decoder part
self.l3 = L.Linear(100,500)
self.l4 = L.Linear(500,1308608)
self.activation = activation
def forward(self,x):
h = self.encode(x)
x_recon = self.decode(h)
return x_recon
def __call__(self,x):
x_recon = self.forward(x)
loss = F.mean_squared_error(h, x)
return loss
def encode(self, x, train=True):
h = F.dropout(self.activation(self.l1(x)), train=train)
return self.activation(self.l2(x))
def decode(self, h, train=True):
h = self.activation(self.l3(h))
return self.l4(x)
You can also refer official Variational Auto Encoder example for the next step: